Daniel Torregrosa


2019

pdf bib
Leveraging Rule-Based Machine Translation Knowledge for Under-Resourced Neural Machine Translation Models
Daniel Torregrosa | Nivranshu Pasricha | Maraim Masoud | Bharathi Raja Chakravarthi | Juan Alonso | Noe Casas | Mihael Arcan
Proceedings of Machine Translation Summit XVII: Translator, Project and User Tracks

pdf bib
Proceedings of the Second Workshop on Multilingualism at the Intersection of Knowledge Bases and Machine Translation
Mihael Arcan | Marco Turchi | Jinhua Du | Dimitar Shterionov | Daniel Torregrosa
Proceedings of the Second Workshop on Multilingualism at the Intersection of Knowledge Bases and Machine Translation

2018

pdf bib
Fast Neural Machine Translation Implementation
Hieu Hoang | Tomasz Dwojak | Rihards Krislauks | Daniel Torregrosa | Kenneth Heafield
Proceedings of the 2nd Workshop on Neural Machine Translation and Generation

This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.

2016

pdf bib
Ranking suggestions for black-box interactive translation prediction systems with multilayer perceptrons
Daniel Torregrosa | Juan Antonio Pérez-Ortiz | Mikel Forcada
Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track

The objective of interactive translation prediction (ITP), a paradigm of computer-aided translation, is to assist professional translators by offering context-based computer-generated suggestions as they type. While most state-of-the-art ITP systems are tightly coupled to a machine translation (MT) system (often created ad-hoc for this purpose), our proposal follows a resourceagnostic approach, one that does not need access to the inner workings of the bilingual resources (MT systems or any other bilingual resources) used to generate the suggestions, thus allowing to include new resources almost seamlessly. As we do not expect the user to tolerate more than a few proposals each time, the set of potential suggestions need to be filtered and ranked; the resource-agnostic approach has been evaluated before using a set of intuitive length-based and position-based heuristics designed to determine which suggestions to show, achieving promising results. In this paper, we propose a more principled suggestion ranking approach using a regressor (a multilayer perceptron) that achieves significantly better results.

2014

pdf bib
Black-box integration of heterogeneous bilingual resources into an interactive translation system
Juan Antonio Pérez-Ortiz | Daniel Torregrosa | Mikel Forcada
Proceedings of the EACL 2014 Workshop on Humans and Computer-assisted Translation